[CvGmt News] [Notiziario] [Settimanale] Fw: avviso Colloquio della Classe di Scienze prof. Nicolò Cesa-Bianchi (15.12.2010)

[Liviana Paoletti]

Inoltro avviso a me pervenuto.
Cordiali saluti
Liviana Paoletti
----- Original Message ----- 
From: Valeria Giuliani 
Sent: Friday, December 03, 2010 10:10 AM
Subject: avviso Colloquio della Classe di Scienze prof. Nicolò Cesa-Bianchi (15.12.2010)


Colloqui della Classe di Scienze


mercoledì 15 dicembre 2010
ore 15.00

 

Scuola Normale Superiore

Pisa

(Aula Mancini)



Nicolò Cesa-Bianchi

Università degli Studi di Milano

 

Terrà  un seminario dal titolo:

 

"The game-theoretic approach to machine learning and adaptation."

 

 

 

Abstract:

The design of artificial systems able to learn and adapt has been one of the main goals of Artificial Intelligence since its very beginning. To this end, statistical modelling has proven to be a tool of extraordinary effectiveness.

In some cases, however, statistics is not the most adequate language for analyzing the interaction between a

learning agent and an ever-changing environment. Indeed, a research thread, emerged in parallel with statistical learning, views this interaction as a repeated game between agent and environment. This different approach allows to analyze, in a rigorous framework, predictive models without any statistical assumptions. In this talk we will trace the roots of the game-theoretic approach in learning theory and describe some of the key results.

 

 

Tutti gli interessati sono invitati a partecipare.

 

 

 

 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cvgmt.sns.it/pipermail/news/attachments/20101203/b85d2a42/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Nicol? Cesa-Bianchi 15.12.10.pdf
Type: application/pdf
Size: 50647 bytes
Desc: not available
URL: <http://cvgmt.sns.it/pipermail/news/attachments/20101203/b85d2a42/attachment-0001.pdf>
-------------- next part --------------
_______________________________________________
Settimanale mailing list
Settimanale at mail.dm.unipi.it
https://mail.dm.unipi.it/listinfo/settimanale
-------------- next part --------------
_______________________________________________
Notiziario mailing list
Notiziario at mail.dm.unipi.it
https://mail.dm.unipi.it/listinfo/notiziario